Search Results for author: Pavitra Krishnaswamy

Found 9 papers, 1 papers with code

Semi-supervised classification of radiology images with NoTeacher: A Teacher that is not Mean

no code implementations10 Aug 2021 Balagopal Unnikrishnan, Cuong Nguyen, Shafa Balaram, Chao Li, Chuan Sheng Foo, Pavitra Krishnaswamy

Specifically, we describe adaptations for scenarios with 2D and 3D inputs, uni and multi-label classification, and class distribution mismatch between labeled and unlabeled portions of the training data.

Classification Image Classification +1

Uncertainty Modeling for Machine Comprehension Systems using Efficient Bayesian Neural Networks

no code implementations COLING 2020 Zhengyuan Liu, Pavitra Krishnaswamy, Ai Ti Aw, Nancy Chen

While neural approaches have achieved significant improvement in machine comprehension tasks, models often work as a black-box, resulting in lower interpretability, which requires special attention in domains such as healthcare or education.

Active Learning Dialogue Generation +2

Self-Path: Self-supervision for Classification of Pathology Images with Limited Annotations

no code implementations12 Aug 2020 Navid Alemi Koohbanani, Balagopal Unnikrishnan, Syed Ali Khurram, Pavitra Krishnaswamy, Nasir Rajpoot

In this paper, we propose a self-supervised CNN approach to leverage unlabeled data for learning generalizable and domain invariant representations in pathology images.

Domain Adaptation General Classification +1

Attention-based Semantic Priming for Slot-filling

no code implementations WS 2018 Jiewen Wu, Rafael E. Banchs, Luis Fern D{'}Haro, o, Pavitra Krishnaswamy, Nancy Chen

The problem of sequence labelling in language understanding would benefit from approaches inspired by semantic priming phenomena.

Language understanding Slot Filling +2

Online Deep Learning: Growing RBM on the fly

no code implementations6 Mar 2018 Savitha Ramasamy, Kanagasabai Rajaraman, Pavitra Krishnaswamy, Vijay Chandrasekhar

The online generative training begins with zero neurons in the hidden layer, adds and updates the neurons to adapt to statistics of streaming data in a single pass unsupervised manner, resulting in a feature representation best suited to the data.

General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.